llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1281 models767 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

knowledge factuality benchmark

AA HLE Text No Tools Leaderboard

May 2025 revision; 2158 text-only questions; no tools; 1 run; pass@1; GPT-5.6 Luna medium judge

Updated Sep 22, 2026

Models100
Model coverage200
Metrichle
EvidenceB

On this page

  • Ranking
  • Highlights
  • Distribution
  • Top models
  • About
  • FAQ

AA HLE Text No Tools Ranking

Higher hle ranks better on this benchmark.

30 of 100 rows
Columns

Show columns

Sort by
Rank
Model
hle
Percentile
Participants
Evidence
Evaluated
Rank01ModelANClaude Fable 5.1Anthropichle59.13%Percentile100.00%Participants200EvidenceBEvaluatedN/A
Rank02ModelANClaude Fable 5Anthropichle55.47%Percentile99.50%Participants200EvidenceBEvaluatedN/A
Rank03ModelANClaude Opus 5Anthropichle54.87%Percentile99.00%Participants200EvidenceBEvaluatedN/A
Rank04ModelOPGPT-6 AstraOpenAIhle54.68%Percentile98.49%Participants200EvidenceBEvaluatedN/A
Rank05ModelOPGPT-5.6 SolOpenAIhle49.49%Percentile97.99%Participants200EvidenceBEvaluatedN/A
Rank06ModelMEMuse Spark 1.3Metahle48.70%Percentile97.49%Participants200EvidenceBEvaluatedN/A
Rank07ModelANClaude Opus 4.8Anthropichle48.66%Percentile96.98%Participants200EvidenceBEvaluatedN/A
Rank08ModelGOGemini 3.7 FlashGooglehle47.87%Percentile96.48%Participants200EvidenceBEvaluatedN/A
Rank09ModelGOGemini 3.8 FlashGooglehle47.82%Percentile95.98%Participants200EvidenceBEvaluatedN/A
Rank10ModelGOGemini 3.1 ProGooglehle47.03%Percentile95.48%Participants200EvidenceBEvaluatedN/A
Rank11ModelMAKimi K3Moonshot AIhle46.90%Percentile94.97%Participants200EvidenceBEvaluatedN/A
Rank12ModelMEMuse Spark 1.1Metahle46.20%Percentile94.47%Participants200EvidenceBEvaluatedN/A
Rank13ModelOPGPT-5.5OpenAIhle45.78%Percentile93.97%Participants200EvidenceBEvaluatedN/A
Rank14ModelMEMuse Spark 1.2Metahle45.46%Percentile93.47%Participants200EvidenceBEvaluatedN/A
Rank15ModelXAGrok 4.6xAIhle44.07%Percentile92.96%Participants200EvidenceBEvaluatedN/A
Rank16ModelOPGPT-5.4OpenAIhle43.74%Percentile92.46%Participants200EvidenceBEvaluatedN/A
Rank17ModelACQwen3.8 MaxAlibaba Cloud / Qwen Teamhle43.10%Percentile91.96%Participants200EvidenceBEvaluatedN/A
Rank18ModelOPGPT-5.6 TerraOpenAIhle42.91%Percentile91.46%Participants200EvidenceBEvaluatedN/A
Rank19ModelGOGemini 3.5 FlashGooglehle42.68%Percentile90.95%Participants200EvidenceBEvaluatedN/A
Rank20ModelXAGrok 4.5xAIhle42.68%Percentile90.45%Participants200EvidenceBEvaluatedN/A
Rank21ModelOPGPT-5.3 CodexOpenAIhle42.49%Percentile89.95%Participants200EvidenceBEvaluatedN/A
Rank22ModelANClaude Opus 4.7Anthropichle42.31%Percentile89.45%Participants200EvidenceBEvaluatedN/A
Rank23ModelZAGLM-5.3Zhipu AIhle42.26%Percentile88.94%Participants200EvidenceBEvaluatedN/A
Rank24ModelANClaude Sonnet 5Anthropichle41.29%Percentile88.44%Participants200EvidenceBEvaluatedN/A
Rank25ModelZAGLM-5.2Zhipu AIhle41.15%Percentile87.94%Participants200EvidenceBEvaluatedN/A
Rank26ModelDEDeepSeek-V4-Pro-0813DeepSeekhle41.01%Percentile87.44%Participants200EvidenceBEvaluatedN/A
Rank27ModelGOGemini 3.6 FlashGooglehle40.82%Percentile86.93%Participants200EvidenceBEvaluatedN/A
Rank28ModelMEMuse SparkMetahle40.69%Percentile86.43%Participants200EvidenceBEvaluatedN/A
Rank29ModelACQwen3.7 MaxAlibaba Cloud / Qwen Teamhle40.50%Percentile85.93%Participants200EvidenceBEvaluatedN/A
Rank30ModelZAGLM-5.3-FlashZhipu AIhle39.85%Percentile85.43%Participants200EvidenceBEvaluatedN/A

AA HLE Text No Tools Highlights

The leading models and scores on this benchmark.

AA HLE Text No Tools Score Distribution

A closer view of the leading scores on this benchmark.

AA HLE Text No Tools

The Top AI Models for AA HLE Text No Tools

The first five results on this benchmark, with official price and output speed added where the model identity can be matched.

What is AA HLE Text No Tools?

What AA HLE Text No Tools measures and how its scores work.

May 2025 revision; 2158 text-only questions; no tools; 1 run; pass@1; GPT-5.6 Luna medium judge

Scores are shown in ratio. This benchmark is verified and has an evidence level of B.

Family
humanity-s-last-exam-no-tools-text-only
Modality
text
Primary category
knowledge factuality
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
overall

Artificial Analysis. Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about AA HLE Text No Tools.

Which model scores highest on AA HLE Text No Tools?

Claude Fable 5.1 is currently ranked first with 59.13%.

What are the top three models on AA HLE Text No Tools?

The current leaders are Claude Fable 5.1 (59.13%), Claude Fable 5 (55.47%), and Claude Opus 5 (54.87%).

Which AA HLE Text No Tools model has the lowest official input price?

Step-3.5-Flash has the lowest matched official input price at $0.10 input / $0.30 output per 1M tokens.

Which models are fastest among AA HLE Text No Tools results?

The fastest matched records are Mercury 2 (1,009.00 tok/s via Inception), GPT OSS 120B (500.00 tok/s via Groq), and GPT-5 mini (348.85 tok/s via OpenAI).

Does the highest hle result prove overall model quality?

No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.

What does AA HLE Text No Tools measure?

May 2025 revision; 2158 text-only questions; no tools; 1 run; pass@1; GPT-5.6 Luna medium judge

Is a higher hle better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

100 model results are currently shown.

Does this benchmark affect the overall score?

Yes. This benchmark can contribute to the current LLMBoard capability score.

Rank #1Claude Fable 5.159.13%
Rank #2Claude Fable 555.47%
Rank #3Claude Opus 554.87%
Rank #4GPT-6 Astra54.68%

Ranking basisThis aa hle text no tools AI model leaderboard uses descending hle in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    AN
    Claude Fable 5.1Anthropic
    hle
    59.13%
    Price
    $10 input / $50 output per 1M tokens
    Speed
    Up to 3.94 tok/s via Anthropic

    Strengths

    • Ranks #1 of 200 compared models
    • 100th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures AA HLE Text No Tools, not total model capability
  2. 02
    AN
    Claude Fable 5Anthropic
    hle
    55.47%
    Price
    $10 input / $50 output per 1M tokens

    Strengths

    • Ranks #2 of 200 compared models
    • 99th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures AA HLE Text No Tools, not total model capability
  3. 03
    AN
    Anthropic
    hle
    54.87%
    Price
    $5.0 input / $25 output per 1M tokens
    Speed
    Up to 4.35 tok/s via Anthropic

    Strengths

    • Ranks #3 of 200 compared models
    • 99th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures AA HLE Text No Tools, not total model capability
  4. 04
    OP
    OpenAI
    hle
    54.68%
    Price
    $10 input / $50 output per 1M tokens
    Speed
    Up to 25.98 tok/s via OpenAI

    Strengths

    • Ranks #4 of 200 compared models
    • 98th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures AA HLE Text No Tools, not total model capability
  5. 05
    OP
    OpenAI
    hle
    49.49%
    Price
    $4.0 input / $20 output per 1M tokens
    Speed
    Up to 35.30 tok/s via OpenAI

    Strengths

    • Ranks #5 of 200 compared models
    • 98th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures AA HLE Text No Tools, not total model capability

Selection summary

Best AI Models for AA HLE Text No Tools

Claude Fable 5.1 currently leads AA HLE Text No Tools with 59.13%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.

Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.

Claude Opus 5
GPT-6 Astra
GPT-5.6 Sol
Benchmark rank #1Claude Fable 5.159.13% · $10 input / $50 output per 1M tokens
Benchmark rank #2Claude Fable 555.47% · $10 input / $50 output per 1M tokens
Benchmark rank #3Claude Opus 554.87% · $5.0 input / $25 output per 1M tokens